linkedin_search_people 10 credits

Find people on LinkedIn by keywords and filters. The right tool when you have a name, role, or 'who is the X at Y' question without a profile URL. Pass keywords (free text: name, title, or both) and any of first_name, last_name, title, school, current_company, past_company. If keywords is omitted it is derived from the name or title filters; school or company filters alone are rejected with INVALID_INPUT, so include keywords with those. Company filters accept a company name, slug, numeric id, or URN. current_company names are matched by LinkedIn's own company search: typo-tolerant and fuzzy, so results can include people whose headline merely mentions the company; when you need exact filtering, pass the numeric id or URN (linkedin_get_company returns both). past_company names are resolved to an id for you. Costs 10 credits including the first 10 results; each further 10 results add 1 credit (limit max 30; trial keys max 10). A cursor page is a NEW call priced the same way by its own limit, so one limit=30 call is much cheaper than three limit=10 pages; prefer a larger limit over paginating. Do NOT combine a past_company NAME or a company-URL filter with limit=30: resolving those spends one of the call's three internal fetches, so that combination is rejected; keep limit<=20 with them or pass the numeric id. current_company names never spend a fetch, so they combine with any limit. Returns name, position, location, urn, public_identifier per result, a cursor for the next page, and total_matches. Results with is_anonymous=true are private profiles; do not pass them to linkedin_get_profile. For one known person with a URL/slug, call linkedin_get_profile directly instead.

Part of the LinkedIn toolset: /docs/linkedin.

Parameters#

REST#

GET /v1/linkedin/search · auth: required · metered: true

curl "https://api.veezee.io/v1/linkedin/search?keywords=CTO&current_company=anthropic" \
  -H "Authorization: Bearer $VEEZEE_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)"

MCP#

{
  "method": "tools/call",
  "params": {
    "name": "linkedin_search_people",
    "arguments": {
      "keywords": "CTO",
      "current_company": "anthropic"
    }
  }
}

Input examples#

Role at a company

{
  "keywords": "CTO",
  "current_company": "anthropic"
}

Name search, more results

{
  "keywords": "John Smith",
  "title": "software engineer",
  "limit": 30
}

Next page

{
  "keywords": "CTO",
  "current_company": "anthropic",
  "cursor": "<cursor from previous response>"
}

Output#

Returns a people_search envelope. Full field list: /docs/fields#people_search.

Errors#

REST returns application/problem+json; MCP returns the same content as an error result. message is written as the next-turn instruction.